📡mleg.tech/feed.xml
📡
This is an RSS feed

Subscribe to get new posts from mleg.tech in your reader of choice.

Format
Atom 1.0
Items
6 entries
Last updated
Jun 14, 2026
Author
Michael Legemah
Agentic AI
What Actually Breaks When You Put LangGraph Agents in Production

Reducer bugs, state bloat, and the deep-merge fix that took a full day to trace — lessons from running multi-agent workflows on AWS Bedrock at scale.

RAG
Chunking Strategy Matters More Than Your Embedding Model

Why fixed-size chunking quietly tanks retrieval quality, and what content-hash dedup buys you at scale.

Eval & testing
LLM-as-a-Judge: Building Quality Gates Into CI/CD

How an eval pipeline caught stale-context regressions before they reached production, and what it cost to build.

AWS
Bedrock + AppSync: A GraphQL Front Door for Agentic Workflows

Decoupling frontend from backend on multi-step AI processes without losing type safety or introducing polling.

Agentic AI
Claude Code as a Force Multiplier, Not a Replacement

What actually changes on a team's velocity and review process once AI-assisted engineering is the default, not the exception.

Career
From Front-End to Principal AI Engineer: What Actually Transferred

A decade of component-driven thinking turned out to be surprisingly good prep for orchestrating agents.

<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
<title>mleg.tech — Michael Legemah</title>
<subtitle>Notes on building AI systems that ship.</subtitle>
<link href="https://mleg.tech/feed.xml" rel="self"/>
<link href="https://mleg.tech/"/>
<id>https://mleg.tech/</id>
<updated>2026-06-14T09:00:00.000Z</updated>
<author>
<name>Michael Legemah</name>
</author>
<entry>
<title>What Actually Breaks When You Put LangGraph Agents in Production</title>
<link href="https://mleg.tech/blog/langgraph-agents-in-production"/>
<id>https://mleg.tech/blog/langgraph-agents-in-production</id>
<published>2026-06-14T09:00:00.000Z</published>
<updated>2026-06-14T09:00:00.000Z</updated>
<summary>Reducer bugs, state bloat, and the deep-merge fix that took a full day to trace — lessons from running multi-agent workflows on AWS Bedrock at scale.</summary>
<category term="Agentic AI"/>
</entry>
<!-- 5 more entries -->
</feed>
mleg.tech — writing on AI systems, shipped and unglamorous.← Back to blog